Analisis Perbandingan Algoritma Decision Tree (C4.5) Dan K-Naive Bayes Untuk Mengklasifikasi Penerimaan Mahasiswa Baru Tingkat Universitas

Suyadi Suyadi, Arief Setyanto, Hanif Al Fattah

Abstract

Profile of PMB (New Student Admissions) students from several periods have abundant data that can be used for research. The data is in the form of student information from the majors of origin, NEM and majors now. Classifying the PMB profile data of students at the University level in Yogyakarta can know the majority of learners. Comparing some algorithms is needed to find out the best algorithm. Classification is a grouping algorithm that has several algorithms such as Decision Tree (C4.5) and K-Naive Bayes. Decision Tree (C4.5) is an algorithm with decision tree, while K-Naive Bayes is the likely algorithm that will occur. This analysis uses Rapidminer which is a data analysis software with features of several algorithms that are easy to operate. Both algorithms have results with large data of 1504 students, Decision tree (C4.5) has an accuracy of 81.84% and an error accuracy of 18.16%, while K-Naive Bayes 85.12% and accuracy of error 14.88%. Whereas with smaller data the Decision tree (C4.5) has 100% accuracy whereas K-Naive Bayes has the same accuracy as Decision Tree (C4.5) that is 100%.

Keywords

Data mining, Classification, Comparison, Decision Tree (C4.5), K-Naive Bayes

Full Text:

PDF

References

Angra, S. and Ahuja, S. (2016) ‘Analysis of student’s data using rapid miner’, Journal on Today’s Ideas - Tomorrow’s Technologies, 4(1), pp. 49–58. doi: 10.15415/jotitt.2016.41004.

Brauning, M. et al. (2017) ‘Lexicographic preferences for predictive modeling of human decision making: A new machine learning method with an application in accounting’, European Journal of Operational Research, 258(1), pp. 295–306. doi: 10.1016/j.ejor.2016.08.055.

Chen, L. and Wang, S. (2012) ‘Automated Feature Weighting In Naive Bayes For High-dimensional Data Classification’, Proceedings of the ACM International Conference on Information and Knowledge Management, pp. 1243–1252. doi: 10.1145/2396761.2398426.

Jannach, D., Jugovac, M. and Lerche, L. (2016) ‘Supporting the Design of Machine Learning Workflows with a Recommendation System’, ACM Transactions on Interactive Intelligent Systems, 6(1), pp. 1–35. doi: 10.1145/2852082.

Kitcharoen, N. et al. (2013) ‘RapidMiner Framework for Manufacturing DataAnalysis on the Cloud’, 2013 10th International Joint Conference on Computer Science and Software Engineering (JCSSE), pp. 1–6. doi: 10.1109/JCSSE.2013.6567336.

S. Rana and A. Singh (2016) ‘Comparative Analysis of Sentiment Orientation Using SVM and Naive Bayes Techniques’, (October), pp. 106–111.

DOI: https://doi.org/10.20961/ijai.v2i1.13258

Refbacks

  • There are currently no refbacks.